Current Issue : April - June Volume : 2014 Issue Number : 2 Articles : 5 Articles
The manufacturing environment rapidly changes in turbulence fashion. Digital\r\nmanufacturing (DM) plays a significant role and one of the key strategies in setting up vision\r\nand strategic planning toward the knowledge based manufacturing. An approach of combining\r\n3D machine vision (3D-MV) and an Additive Manufacturing (AM) may finally be finding its\r\nniche in manufacturing. This paper briefly overviews the integration of the 3D machine vision\r\nand AM in concurrent product and process development, the challenges and opportunities, the\r\nimplementation of the 3D-MV and AM at POLMAN Bandung in accelerating product design\r\nand process development, and discusses a direct deployment of this approach on a real case\r\nfrom our industrial partners that have placed this as one of the very important and strategic\r\napproach in research as well as product/prototype development. The strategic aspects and\r\nneeds of this combination approach in research, design and development are main concerns of\r\nthe presentation....
An illumination normalization method for face recognition has been developed since it was difficult to control lighting conditions\r\nefficiently in the practical applications. Considering that the irradiation light is of little variation in a certain area, a mean estimation\r\nmethod is used to simulate the illumination component of a face image. Illumination component is removed by subtracting the\r\nmean estimation from the original image. In order to highlight face texture features and suppress the impact of adjacent domains,\r\na ratio of the quotient image and its modulus mean value is obtained.The exponent result of the ratio is closely approximate to a\r\nrelative reflection component. Since the gray value of facial organs is less than that of the facial skin, postprocessing is applied to\r\nthe images in order to highlight facial texture for face recognition. Experiments show that the performance by using the proposed\r\nmethod is superior to that of state of the arts....
When independent component analysis (ICA) is applied to color natural images, the representation it learns has spatiochromatic\r\nproperties similar to the responses of neurons in primary visual cortex. Existing models of ICA have only been applied to pixel\r\npatches. This does not take into account the space-variant nature of human vision. To address this, we use the space-variant logpolar\r\ntransformation to acquire samples fromcolor natural images, and then we apply ICA to the acquired samples.We analyze the\r\nspatiochromatic properties of the learned ICA filters. Qualitatively, the model matches the receptive field properties of neurons in\r\nprimary visual cortex, including exhibiting the same opponent-color structure and a higher density of receptive fields in the foveal\r\nregion compared to the periphery.We also adopt the ââ?¬Å?self-taught learningââ?¬Â paradigm from machine learning to assess the modelââ?¬â?¢s\r\nefficacy at active object and face classification, and the model is competitive with the best approaches in computer vision...
A new method for detecting rooftops in satellite images is presented. The proposed method is based on a combination of machine\r\nlearning techniques, namely, k-means clustering and support vector machines (SVM). Firstly k-means clustering is used to segment\r\nthe image into a set of rooftop candidatesââ?¬â?these are homogeneous regions in the image which are potentially associated with\r\nrooftop areas. Next, the candidates are submitted to a classification stage which determines which amongst them correspond to\r\nââ?¬Å?trueââ?¬Â rooftops. To achieve improved accuracy, a novel two-pass classification process is used. In the first pass, a trained SVM is\r\nused in the normal way to distinguish between rooftop and nonrooftop regions.However, this can be a challenging task, resulting in\r\na relatively high rate of misclassification. Hence, the second pass, which we call the ââ?¬Å?histogram method,ââ?¬Â was devised with the aim\r\nof detecting rooftops which were missed in the first pass. The performance of the model is assessed both in terms of the percentage\r\nof correctly classified candidates as well as the accuracy of the estimated rooftop area....
Bundle adjustment is one of the essential components of the computer vision toolbox. This paper revisits the resection-intersection\r\napproach, which has previously been shown to have inferior convergence properties. Modifications are proposed that greatly\r\nimprove the performance of this method, resulting in a fast and accurate approach. Firstly, a linear triangulation step is added\r\nto the intersection stage, yielding higher accuracy and improved convergence rate. Secondly, the effect of parameter updates is\r\ntracked in order to reduce wasteful computation; only variables coupled to significantly changing variables are updated. This leads\r\nto significant improvements in computation time, at the cost of a small, controllable increase in error. Loop closures are handled\r\neffectively without the need for additional networkmodelling.The proposed approach is shown experimentally to yield comparable\r\naccuracy to a full sparse bundle adjustment (20% error increase) while computation time scales much better with the number of\r\nvariables. Experiments on a progressive reconstruction system show the proposed method to be more efficient by a factor of 65 to\r\n177, and 4.5 times more accurate (increasing over time) than a localised sparse bundle adjustment approach....
Loading....